summaryrefslogtreecommitdiff
path: root/csum-file.c
blob: 59ef3398ca2b01676055fff40b80ac7896f87ffc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
/*
 * csum-file.c
 *
 * Copyright (C) 2005 Linus Torvalds
 *
 * Simple file write infrastructure for writing SHA1-summed
 * files. Useful when you write a file that you want to be
 * able to verify hasn't been messed with afterwards.
 */
#include "cache.h"
#include "progress.h"
#include "csum-file.h"

static void verify_buffer_or_die(struct hashfile *f,
				 const void *buf,
				 unsigned int count)
{
	ssize_t ret = read_in_full(f->check_fd, f->check_buffer, count);

	if (ret < 0)
		die_errno("%s: sha1 file read error", f->name);
	if (ret != count)
		die("%s: sha1 file truncated", f->name);
	if (memcmp(buf, f->check_buffer, count))
		die("sha1 file '%s' validation error", f->name);
}

static void flush(struct hashfile *f, const void *buf, unsigned int count)
{
	if (0 <= f->check_fd && count)
		verify_buffer_or_die(f, buf, count);

	if (write_in_full(f->fd, buf, count) < 0) {
		if (errno == ENOSPC)
			die("sha1 file '%s' write error. Out of diskspace", f->name);
		die_errno("sha1 file '%s' write error", f->name);
	}

	f->total += count;
	display_throughput(f->tp, f->total);
}

void hashflush(struct hashfile *f)
{
	unsigned offset = f->offset;

	if (offset) {
		the_hash_algo->update_fn(&f->ctx, f->buffer, offset);
		flush(f, f->buffer, offset);
		f->offset = 0;
	}
}

static void free_hashfile(struct hashfile *f)
{
	free(f->buffer);
	free(f->check_buffer);
	free(f);
}

int finalize_hashfile(struct hashfile *f, unsigned char *result,
		      enum fsync_component component, unsigned int flags)
{
	int fd;

	hashflush(f);
	the_hash_algo->final_fn(f->buffer, &f->ctx);
	if (result)
		hashcpy(result, f->buffer);
	if (flags & CSUM_HASH_IN_STREAM)
		flush(f, f->buffer, the_hash_algo->rawsz);
	if (flags & CSUM_FSYNC)
		fsync_component_or_die(component, f->fd, f->name);
	if (flags & CSUM_CLOSE) {
		if (close(f->fd))
			die_errno("%s: sha1 file error on close", f->name);
		fd = 0;
	} else
		fd = f->fd;
	if (0 <= f->check_fd) {
		char discard;
		int cnt = read_in_full(f->check_fd, &discard, 1);
		if (cnt < 0)
			die_errno("%s: error when reading the tail of sha1 file",
				  f->name);
		if (cnt)
			die("%s: sha1 file has trailing garbage", f->name);
		if (close(f->check_fd))
			die_errno("%s: sha1 file error on close", f->name);
	}
	free_hashfile(f);
	return fd;
}

void hashwrite(struct hashfile *f, const void *buf, unsigned int count)
{
	while (count) {
		unsigned left = f->buffer_len - f->offset;
		unsigned nr = count > left ? left : count;

		if (f->do_crc)
			f->crc32 = crc32(f->crc32, buf, nr);

		if (nr == f->buffer_len) {
			/*
			 * Flush a full batch worth of data directly
			 * from the input, skipping the memcpy() to
			 * the hashfile's buffer. In this block,
			 * f->offset is necessarily zero.
			 */
			the_hash_algo->update_fn(&f->ctx, buf, nr);
			flush(f, buf, nr);
		} else {
			/*
			 * Copy to the hashfile's buffer, flushing only
			 * if it became full.
			 */
			memcpy(f->buffer + f->offset, buf, nr);
			f->offset += nr;
			left -= nr;
			if (!left)
				hashflush(f);
		}

		count -= nr;
		buf = (char *) buf + nr;
	}
}

struct hashfile *hashfd_check(const char *name)
{
	int sink, check;
	struct hashfile *f;

	sink = xopen("/dev/null", O_WRONLY);
	check = xopen(name, O_RDONLY);
	f = hashfd(sink, name);
	f->check_fd = check;
	f->check_buffer = xmalloc(f->buffer_len);

	return f;
}

static struct hashfile *hashfd_internal(int fd, const char *name,
					struct progress *tp,
					size_t buffer_len)
{
	struct hashfile *f = xmalloc(sizeof(*f));
	f->fd = fd;
	f->check_fd = -1;
	f->offset = 0;
	f->total = 0;
	f->tp = tp;
	f->name = name;
	f->do_crc = 0;
	the_hash_algo->init_fn(&f->ctx);

	f->buffer_len = buffer_len;
	f->buffer = xmalloc(buffer_len);
	f->check_buffer = NULL;

	return f;
}

struct hashfile *hashfd(int fd, const char *name)
{
	/*
	 * Since we are not going to use a progress meter to
	 * measure the rate of data passing through this hashfile,
	 * use a larger buffer size to reduce fsync() calls.
	 */
	return hashfd_internal(fd, name, NULL, 128 * 1024);
}

struct hashfile *hashfd_throughput(int fd, const char *name, struct progress *tp)
{
	/*
	 * Since we are expecting to report progress of the
	 * write into this hashfile, use a smaller buffer
	 * size so the progress indicators arrive at a more
	 * frequent rate.
	 */
	return hashfd_internal(fd, name, tp, 8 * 1024);
}

void hashfile_checkpoint(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
	hashflush(f);
	checkpoint->offset = f->total;
	the_hash_algo->clone_fn(&checkpoint->ctx, &f->ctx);
}

int hashfile_truncate(struct hashfile *f, struct hashfile_checkpoint *checkpoint)
{
	off_t offset = checkpoint->offset;

	if (ftruncate(f->fd, offset) ||
	    lseek(f->fd, offset, SEEK_SET) != offset)
		return -1;
	f->total = offset;
	f->ctx = checkpoint->ctx;
	f->offset = 0; /* hashflush() was called in checkpoint */
	return 0;
}

void crc32_begin(struct hashfile *f)
{
	f->crc32 = crc32(0, NULL, 0);
	f->do_crc = 1;
}

uint32_t crc32_end(struct hashfile *f)
{
	f->do_crc = 0;
	return f->crc32;
}

int hashfile_checksum_valid(const unsigned char *data, size_t total_len)
{
	unsigned char got[GIT_MAX_RAWSZ];
	git_hash_ctx ctx;
	size_t data_len = total_len - the_hash_algo->rawsz;

	if (total_len < the_hash_algo->rawsz)
		return 0; /* say "too short"? */

	the_hash_algo->init_fn(&ctx);
	the_hash_algo->update_fn(&ctx, data, data_len);
	the_hash_algo->final_fn(got, &ctx);

	return hasheq(got, data + data_len);
}